Visibility-Aware Pixelwise View Selection for Multi-View Stereo Matching
Not on the map. Why?
Abstract (arXiv)
The performance of PatchMatch-based multi-view stereo algorithms depends heavily on the source views selected for computing matching costs. Instead of modeling the visibility of different views, most existing approaches handle occlusions in an ad-hoc manner. To address this issue, we propose a novel visibility-guided pixelwise view selection scheme in this paper. It progressively refines the set of source views to be used for each pixel in the reference view based on visibility information provided by already validated solutions. In addition, the Artificial Multi-Bee Colony (AMBC) algorithm is employed to search for optimal solutions for different pixels in parallel. Inter-colony communication is performed both within the same image and among different images. Fitness rewards are added to validated and propagated solutions, effectively enforcing the smoothness of neighboring pixels and allowing better handling of textureless areas. Experimental results on the DTU dataset show our method achieves state-of-the-art performance among non-learning-based methods and retrieves more details in occluded and low-textured regions.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 24 of its 52 references that are in the map. First posted on arXiv 14 Feb 2023.
Builds on
24 of 52 references.
References · 24
- 2018Occupancy Networks: Learning 3D Reconstruction in Function Spacecited by 2,037
- 2019KPConv: Flexible and Deformable Convolution for Point Cloudscited by 1,202
- 2018Learning Implicit Fields for Generative Shape Modelingcited by 1,060
- 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
- 2018MVSNet: Depth Inference for Unstructured Multi-view Stereocited by 780
- 2019Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervisioncited by 699
- 20163D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstructioncited by 587
- 2019PointFlow: 3D Point Cloud Generation with Continuous Normalizing Flowscited by 487
- 2019BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networkscited by 487
- 2019Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matchingcited by 414
- 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
- 2019Recurrent MVSNet for High-resolution Multi-view Stereo Depth Inferencecited by 252
12 more
- 2020MetaSDF: Meta-learning Signed Distance Functionscited by 214
- 2020PatchmatchNet: Learned Multi-View Patchmatch Stereocited by 204
- 2021NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereocited by 191
- 2017Octree Generating Networks: Efficient Convolutional Architectures for High-resolution 3D Outputscited by 189
- 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
- 2017SurfaceNet: An End-to-end 3D Neural Network for Multiview Stereopsiscited by 128
- 2019Multi-Scale Geometric Consistency Guided Multi-View Stereocited by 105
- 2022Rethinking Depth Estimation for Multi-View Stereo: A Unified Representationcited by 82
- 2019Planar Prior Assisted PatchMatch Multi-View Stereocited by 57
- 2019A Skeleton-bridged Deep Learning Approach for Generating Meshes of Complex Topologies from Single RGB Imagescited by 37
- 2019TAPA-MVS: Textureless-Aware PAtchMatch Multi-View Stereocited by 34
- 2020SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces from RGB Imagescited by 30
Built on by
Citing papers per year: 2025: 2.
2 papers.